EUVIMEDEUVIMED entdecken
Crossref

Learning Topology-Aware Dynamic Associations for Robust Multi-Person Pose Estimation

Shengnan Hu, Yandong Liu, Jiangnan Liu, Yahong Chen

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (6) · 4914-4922

DOI: 10.1609/aaai.v40i6.42495 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Shengnan Hu und 3 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multi-person pose estimation in real-world scenarios remains a challenging task due to frequent occlusions, scale variations, and complex human interactions. Existing methods often rely on fixed keypoint association patterns that fail to capture the dynamic and context-dependent nature of human body topologies, leading to misalignment and false detections. In this work, we propose a topology-aware dynamic association framework that adaptively models inter-keypoint relationships conditioned on local context and pose topology. The proposed framework comprises three stages: a human-to-keypoint detection module for coarse localization, a dynamic keypoint association module that learns flexible connectivity patterns between joints, and a fine-grained refinement module for precise pose adjustment. By integrating topological priors into dynamic learning and multi-stage optimization, our proposed method effectively mitigates the issues caused by occlusions and overlapping instances. Extensive experiments on benchmark datasets demonstrate that our approach achieves state-of-the-art performance, especially in crowded and occlusion-heavy scenes.

Zitieren

APA

Hu, S., Liu, Y., Liu, J., & Chen, Y. (2026). Learning Topology-Aware Dynamic Associations for Robust Multi-Person Pose Estimation. Proceedings of the AAAI Conference on Artificial Intelligence, 40(6), 4914-4922. https://doi.org/10.1609/aaai.v40i6.42495

Vancouver

Hu S, Liu Y, Liu J, Chen Y. Learning Topology-Aware Dynamic Associations for Robust Multi-Person Pose Estimation. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(6):4914-4922. doi:10.1609/aaai.v40i6.42495

BibTeX
@article{Hu2026,
  author = {Hu, Shengnan and Liu, Yandong and Liu, Jiangnan and Chen, Yahong},
  title = {Learning Topology-Aware Dynamic Associations for Robust Multi-Person Pose Estimation},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {6},
  pages = {4914--4922},
  doi = {10.1609/aaai.v40i6.42495}
}
Kostenlos starten →